The real question is, what family? lol

Presentation Skills: 100000/10

Allen is hilarious!

15:32

Hello, and thank you for this package. I wanted to add an offset to my model, but I realize that it's not possible. An offset can be seen as a linear predictor with a variable having a fixed coefficient of 1 (g(mu) = f(x1) +x2 ) : x2 is an offset. Please, is it possible to fix the value of the coefficient in a linear term? For example, l(1, coef_estimate=1)? In this case, variable 1 (x2) will behave like an offset.

Very cool! It's so hard to find good things about data science without reading academic papers, and this video is 7 years old. It seems that the data science community is very stingy about sharing its knowledge or that we have very few data scientists.

I feel like Daniel and Leonard's characters in The Big Bang Theory have a lot of similarities. Did anyone else notice that?

great talk raymond!

Great talk! Possible to have a link to the code?

Amazing !

My question is: is collider bias different than usual multivariable modelling where you have models a lot of time adjust for say age and sex and you see that in a lot of statistical papers and you put variables in a model if their value is significant but here you say that would bias a variable you interested in seeing the casual effect is that true

thank you so much for sharing with us!

cool stuff, could you share the slides?

Good!

Carlos es un crack, casi 5 años después sigue siendo esto totalmente útil!!!

Fascinating approach.

is it called the back-end because its where the shit goes?

sticky stuff is interest rates

Good

I can't believe how good this instructor is. This is a terrific live demo training course.

For sure

Dik Ondra!

what a lion on this video, speaker is a G.O.A.T. , you know?

7:54 muscle memory.

One of the most informative CS videos I've ever seen...

🎉 "Promosm"

duckdb is the best! i would really like to have an apache arrow sql grpc server for it. this would solve multi user access.

21 century, AI is seating at the table with us, but we still spend 2 mins out 4 to set up screen, wires and throw out a handmade dice. Makes an impression of 'good manners' social bootcamp. Probably it could be compiled into a nice short video for youtube.

Beautiful...

like like like

Why did they keep interrupting??

Sound to video is missing…

Work of love

Is the pipeline the equivalent of a fluent interface in pandas/scikit world?

Colleen is one of maybe 5 people, including Dr. Peter Flom that are actually people of quality in statistics and data science. Touching on this epidemic issue, seeing as I can direct myself to a focused, properly expressive attitude on it… What points of interaction even exist to manage epidemic spreads that have a sufficient expected value of viability and how would we even determine what the minimum value should be? Would the needed simulation model be doable in tier 2 or below because it took a liter of sweat just to get FreeMat on my computer to help with performance threatening illness in U.S. residents 😂

please share the code

DuckDB really changed the way I interact with data frames. I was moving from pandas to polars because of the speed and better API but now that’s completely irrelevant: I just load data into either library and almost all my processing happens in DuckDB with SQL.

great talk, thank you very much!

A python i would not advise. It needs a doctor for its eyes....Just made a short visit to Mary

Hi, Mark Hamazaspyan. I would to talk to you about a project to identity utility pole.

I'll take Polars seriously when employers ask for certification. Till that happens, I see enterprises unable to uproot themselves from pandas.

Great overview

Sectarianism aplenty!

I was trying to learn pandas just as Polars was coming out and I'm glad I switched to Polars. I was so frustrated with pandas nonsensical quirks and inconsistencies. It didn't seem to follow any conventions I'd ever seen. Maybe there was some statistics or math standard that I'm not familiar with, but as a programmer, Polars has a beautiful API that does what I expect it to do.

Video is very basic. If you have tried polars already don’t waist your time

Lazy processing with scan_parquet and sink_parquet is pretty good, use it all the time. I usually have 10's, or even 100 GB's of csv's. Just scan through it dump to parquet (still bigger than I could keep in memory), then break it apart with sink/scan and duckdb.

The polars learning curve was tougher for me than dask but performance is consistent 👍🏾

good overview, thanks!

Previously used Pandas but the speed and syntax are just so much better and more consistent in Polars (after the initial learning curve) I only switch back to Pandas if HAVE to (usually GIS related). Also, one update since this talk was given, it was announced that Polars will also be getting GPU support via Rapids (same project that brought GPU support to Pandas)

Wow, this is the kind of content, keep me visiting youtube.